Skip to content

Gemini 2.5 Pro Preview (Jun 2025)

ModelActive
by Google · family “gemini-pro-preview-jun”
Epoch Capabilities Index
Not scored by Epoch AI
Released
5 Jun 2025
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (18)

BenchmarkDomainScorevs best recordedSettingRunSource
Remote Labor Indexagents0.8%
4%
——External ↗
FrontierMath-Tier-4-2025-07-01-Privatesupersededmath2.1% ±2.1
4%
—3 Jul 2025Epoch ↗
DeepResearch Benchagents42.8%
77%
——External ↗
GSO-Benchcoding3.9%
8%
——External ↗
ARC-AGI-2reasoning0.0%
0%
1K—External ↗
METR Time Horizonsagents55.4%
65%
——External ↗
GeoBenchmultimodal86.0%
98%
——External ↗
FrontierMath-2025-02-28-Privatesupersededmath10.3% ±1.8
20%
—3 Jul 2025Epoch ↗
Fiction.LiveBenchlong-context91.7%
94%
——External ↗
Lech Mazur Writingother80.9%
94%
——External ↗
VPCTmultimodal46.4%
51%
——External ↗
HLEknowledge21.6%
39%
——External ↗
Aider polyglotcoding83.1%
94%
32K—External ↗
The Agent Companyagents30.3%
71%
——External ↗
SimpleBenchreasoning62.4%
76%
——External ↗
GPQA diamondscience84.8% ±2.6
89%
—5 Jun 2025Eval log ↗
MATH level 5math95.9% ±0.4
98%
—8 May 2025Epoch ↗
ARC-AGIreasoning31.3%
32%
1K—External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens
This model has no public API price listing

0 recorded prices on — (OpenRouter listing); re-read on every data refresh, most recently 8h ago. Steps show when the price changed.

Events

No events recorded yet.